© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8131
    Prev
    Next
    INDEX
    Explanations

    past performance not indicative

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects disclaimer or exclusion statements in product descriptions (e.g. “other accessories not included,” “photos are for reference only”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ErrorCode
    0.77
    User
    0.72
    AuthState
    0.69
    UserPool
    0.69
    Errors
    0.68
    '=>
    0.66
    UserInfo
    0.66
    Assets
    0.65
    ссия
    0.65
    EMAIL
    0.65
    POSITIVE LOGITS
    r
    0.84
    ك
    0.71
     తాగ
    0.68
    ج
    0.68
    gleichen
    0.66
     zeigt
    0.66
    kového
    0.66
     खेल
    0.65
     वातावर
    0.65
     genannten
    0.65
    Activations Density 0.000%

    No Known Activations